library(tidyverse)
library(janitor)
library(lubridate)
library(here)
library(paletteer)
library(tsibble)
library(fable)
library(fabletools)
library(feasts)
library(forecast)
library(sf)
library(tmap)
library(mapview)
us_renew <- read_csv(here("data", "renewables_cons_prod.csv")) %>%
clean_names()
renew_clean <- us_renew %>%
mutate(description = str_to_lower(description)) %>%
filter(str_detect(description, pattern = "consumption")) %>%
filter(!str_detect(description, pattern = "total"))
renew_date <- renew_clean %>%
mutate(yr_mo_day = lubridate::parse_date_time(yyyymm, "ym")) %>%
mutate(month_sep = yearmonth(yr_mo_day)) %>%
mutate(value = as.numeric(value)) %>%
drop_na(month_sep, value)
# Make a version where I have month and year in separate columns
renew_parsed <- renew_date %>%
mutate(month = month(yr_mo_day, label = TRUE)) %>%
mutate(year = year(yr_mo_day))
renew_gg <- ggplot(data = renew_date,
aes(x = month_sep,
y = value,
group = description)) +
geom_line(aes(color = description))
renew_gg
Updating my colors with paletteer palettes:
renew_gg +
scale_color_paletteer_d("DresdenColor::bloodrites")
renew_ts <- as_tsibble(renew_parsed, key = description, index = month_sep)
Let’s look at our ts data in a couple different ways:
renew_ts %>% autoplot(value)
# this works because the key was already specified as description above
renew_ts %>% gg_subseries(value)
# renew_ts %>% gg_season(value) - doesn't always work
ggplot(data = renew_parsed,
aes(x = month,
y = value,
group = year)) +
geom_line(aes(color = year)) +
facet_wrap(~description,
ncol = 1,
scales = "free",
strip.position = "right")
hydro_ts <- renew_ts %>%
filter(description == "hydroelectric power consumption")
hydro_ts %>% autoplot(value)
hydro_ts %>% gg_subseries(value)
ggplot(hydro_ts, aes(x = month, y = value, group = year)) +
geom_line(aes(color = year))
hydro_quarterly <- hydro_ts %>%
index_by(year_qu = ~(yearquarter(.))) %>%
summarize(avg_consumption = mean(value))
head(hydro_quarterly)
## # A tsibble: 6 x 2 [1Q]
## year_qu avg_consumption
## <qtr> <dbl>
## 1 1973 Q1 261.
## 2 1973 Q2 255.
## 3 1973 Q3 212.
## 4 1973 Q4 225.
## 5 1974 Q1 292.
## 6 1974 Q2 290.
dcmp <- hydro_ts %>%
model(STL(value ~ season(window = 5)))
# window specifies moving avg window
# value as a function of season
components(dcmp) %>% autoplot()
# residual component is usually less than 10% of total range of values (e.g. here it ranges from about 150 - 300 trillion BTUs, errors about 20)